EP4185951A1 - Software-aktualisierung über eine funkverbindung - Google Patents
Software-aktualisierung über eine funkverbindungInfo
- Publication number
- EP4185951A1 EP4185951A1 EP21749092.9A EP21749092A EP4185951A1 EP 4185951 A1 EP4185951 A1 EP 4185951A1 EP 21749092 A EP21749092 A EP 21749092A EP 4185951 A1 EP4185951 A1 EP 4185951A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- vehicle
- software
- update
- machine learning
- fleet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
Definitions
- the present invention relates to a method for updating software in vehicles in a vehicle fleet, an updating system which carries out such an update on vehicles in the fleet, such a vehicle and a background device and an updating device of the updating system.
- Modern vehicles are equipped with a large number of electronic, software-controlled components that control and implement vehicle functions.
- ECU Electronic Control Unit
- the software installed in such control systems is usually operating software or firmware that specifies the behavior of the relevant components or ECUs and must be updated regularly, for example by installing updates and/or patches, particularly for security reasons that replace parts of the Software or the Software as a whole.
- updating or software updating means a process with which up-to-date software available on a server is first downloaded to the vehicle, stored in a suitable memory and then installed in the correct control units and components.
- the previous software is replaced by the downloaded, current software and, if necessary, configured in such a way that it takes over the tasks of the previous software when executed by a microprocessor.
- a suitable radio link is mainly required for downloading the software to the vehicle
- installing or configuring the current software in the vehicle may also require a radio link, for example to download configuration data from the server or specific data such as keys, checksums, identifiers, references or the like to the server.
- the term "update” or "software update” means in particular that part of this process for which a stable radio connection is required.
- a main aspect of the invention in order to update software in vehicles in a vehicle fleet, those vehicles in the fleet whose software is to be updated are first identified. In this step, at least one of the vehicles in the vehicle fleet is selected, the software of which is then updated via an existing radio link according to predetermined update conditions.
- the update conditions are determined according to the invention by means of a machine learning model or "machine learning model”, also referred to below as an ML model, which models transmission qualities of as many different radio links as possible via a radio network, i.e. of radio links at different times and at different times Locating the radio network
- the ML model can therefore be compared to a time-variable, changeable map that maps the transmission qualities of radio connections with a specific spatial resolution, for example corresponding to the radio cells of a mobile radio network, and does so with a specific time-dependent Time resolution over a reasonable period of time, for example a day, a week, or a month.
- This ML model is the result of an ongoing training process that will be described below.
- the trained ML model is used to derive predictions regarding the transmission quality of radio connections, via which the software of the at least one identified vehicle can be updated in the future.
- the update conditions are then determined in such a way that they specify one or more possible future radio links with sufficient accuracy, the predicted transmission qualities of which are sufficient to update the vehicle's software.
- a “future radio connection” in this context means such a radio connection that the vehicle can potentially establish and maintain in the future in order to update the software via this radio connection as soon as it is established.
- the ML model says in other words, the update conditions under which the vehicle's software can be updated with a sufficiently high probability in such a way that the disadvantages of the prior art described at the outset are avoided.
- the ML model predicts a transmission quality that is sufficient within the meaning of the invention for a radio connection if it is likely to be suitable for successfully completing the process of updating the software as soon as it is started. It is in the nature of predictions made by a machine learning model that they do not have to apply, but only probably apply. An unexpectedly high volume of traffic in certain radio cells, for example due to a construction site in other radio cells, can worsen the actual transmission quality of a radio connection contrary to the forecast.
- the ML model generated by training which models transmission qualities of potential radio links, is the basis for a prediction of the circumstances under which the software of the relevant Vehicle can be expected to be updated without interruption. These circumstances of the non-disruptive update are described by update conditions. If the software is updated in accordance with the update conditions, the disadvantages of the prior art described above can probably be avoided.
- the updating method according to the invention is carried out by an updating system which comprises a background device and at least one updating device which is in contact with the background device via a data communication connection.
- the updating device identifies the vehicles whose software is to be updated, establishes the radio connections required for this to the vehicles and finally updates the software of the identified vehicles in accordance with the specified update conditions.
- the ML model which models transmission qualities of potential radio connections, is set up on the background device.
- the machine learning model set up on a background device determines the individual update conditions for updating the software of each identified vehicle in such a way that the update conditions each describe radio connections for which according to Prediction sufficient transmission qualities are to be expected.
- the software of the vehicles in question can be updated according to the invention, preferably without interruption and/or within a predetermined time window, within which the software update is started and completely ended.
- a vehicle is set up in such a way that its software can be updated by an update system according to the invention in the manner according to the invention.
- a vehicle according to the invention includes means for setting up a radio link according to the specification of the update conditions and for downloading and installing up-to-date software in the relevant control units and ECU components.
- the transmission quality which the machine learning model uses as a basis for determining update conditions, is preferably a data transmission rate or data rate, i.e. a measure of the digital data volume within a specific period of time and at a specific location, for example within a radio cell , can be transmitted via the relevant radio link.
- a data transmission rate or data rate i.e. a measure of the digital data volume within a specific period of time and at a specific location, for example within a radio cell .
- the more participants (probably) register in a radio cell at the same time or within the same period of time, i.e. the more parallel radio connections (probably) exist, the lower the (probable) data rate of each of these radio connections.
- Adequate transmission quality within the meaning of the invention is thus predicted by the ML model in particular when a radio connection PHg a data rate is expected that exceeds a specified minimum data rate for a specific period, so that the software can be updated within this period.
- update conditions are determined according to which the vehicle can probably carry out the software update without interruption as soon as these apply.
- the digital size or the data volume of the current software to be downloaded via the radio link is also taken into account and the update conditions are defined accordingly such that the minimum data rate is exceeded long enough to be able to completely update the software.
- the update conditions are determined in particular in such a way that the radio connection is sufficiently stable over time, ie it is available long enough without interruption to update the software.
- Such a specified probability is, for example, greater than 0.8 (> 80%), greater than 0.9 (> 90%) or greater than 0.95 (> 95%) or greater than 0.98 (> 98%) .
- the update conditions preferably include at least one time condition and at least one location condition. At least one pair of conditions is preferably determined, consisting of a time condition and a location condition.
- the software is then automatically updated as soon as one of the pairs of conditions that the ML model has determined for the vehicle in question are met; if the vehicle satisfies both the location and the time condition.
- a radio cell or a specific location, a section of road or an area in which the software of the relevant vehicle must be updated is determined as a location condition, for example.
- the time condition preferably specifies a time interval within which the software is to be updated while the vehicle simultaneously meets the location condition.
- the time interval is dimensioned in such a way that the software can be completely updated with the associated predicted transmission quality.
- the ML model is also trained by the central background facility. Specifically, all processes and operations related to the creation, training, and use of the ML model are performed by the backend facility. The ML model is first trained with training data in order then, in a subsequent step, to use the ML model to make predictions regarding the transmission qualities of radio links or to derive them from the trained ML model and to determine suitable update conditions .
- a large number of sensor data are therefore collected from the vehicles in the vehicle fleet as training data, which are forwarded to the background device via an updating device and are used there as training data for the ML model.
- This sensor data includes, in particular, measured values of the specific transmission qualities or data rates of radio connections, including the associated location and time data, which are collected from the vehicles during their regular ferry operations.
- Other sensor data which is preferably also used to train the ML model, relates to information on the number of active radio connections within radio cells at specific times or within specific time intervals, as well as information on the specific routes of the vehicles, i.e. on the movement patterns of the vehicles through the radio network and the radio cells visited, including the corresponding time information.
- the update device does not simply forward this sensor data to the background device, but rather processes it if necessary.
- a single vehicle may not be able to take measurements of the number of wireless connections active at a point in time, so that the updating device preferably evaluates the sensor data from many vehicles in order to derive such information from them.
- radio connections Based on the transmission qualities measured by the vehicles in certain radio cells at certain times, possible transmission qualities of radio connections for which no sensor data are available are derived when training the ML model.
- the transmission qualities of such radio connections are therefore estimated during training or extrapolated from the available sensor data, for example using sensor data from radio cells or for time intervals with similar characteristics.
- the proximity of a radio cell for which there is no or insufficient sensor data to other radio cells for which sufficient sensor data has been collected can have a similar characteristic, or comparable traffic volumes in two radio cells, similar population densities, or the like.
- Radio cells are preferably grouped into clusters on the basis of such and other characteristics, and sensor data for one or a few radio cells in a cluster are used for all other radio cells in the cluster.
- the ML model trained in this way is then used to make predictions about the transmission qualities of radio connections for a vehicle whose software is to be updated, which this vehicle could potentially use in the future to update its software. This is preferably based on the movement data of the vehicle so that only radio connections are taken into account that the vehicle can also realistically set up during its normal operation, for example on regularly repeated journeys.
- the ML model selects one or more of these radio links for which sufficiently stable transmission qualities are predicted and which are preferably matched to the movement data of the vehicle.
- the update conditions according to which the software of the relevant vehicle is updated then describe the selected radio links with potentially adequate transmission qualities. For example, if the ML model is on the morning commute on a certain day of the week and on the evening commute on another working day
- the update conditions describe locations or radio cells and points in time or time intervals of these two situations, so that two different options are offered for updating the software.
- update conditions are determined for all identified vehicles and combined into an update plan that forms the basis of an update campaign that updates the software of all identified vehicles within a specified time frame.
- the ML model is therefore provided with the list of all identified vehicles whose software is to be updated, the corresponding time specifications with regard to the desired time horizon of the update campaign, and the movement data of the vehicles in question.
- update conditions are not determined for each individual vehicle independently of those of other vehicles, but rather that an optimal update plan is found that minimizes a higher-level cost function or maximizes a higher-level utility function.
- Such a function is optimal when transmission qualities matched to their movement data are predicted for as many vehicles as possible and update conditions are found that do not collide with one another.
- the update conditions can either be monitored and implemented by the update device or autonomously by each vehicle itself.
- sensitive personal data such as the sensor and/or movement data used as training data for the ML model
- provide information about whereabouts and times of people and are therefore valid may be subject to data protection regulations, leave the respective vehicle and thereby potentially become accessible to unauthorized persons.
- the invention described above can also be implemented as a “federated learning” variant.
- “Federated leaming” is a distributed or decentralized approach to machine learning in which local instances of an ML model be trained decentrally based on individual, local training data.
- a local, vehicle-specific ML model is installed on several vehicles, preferably on all vehicles in the vehicle fleet, which is trained based solely on the sensor and/or movement data of the relevant individual vehicle.
- the vehicles or their vehicle-specific ML models do not exchange any personal (training) data with one another or with the background or update device.
- a corresponding, higher-level and fleet-wide ML model is operated on the background device, which on the one hand integrates the local training results of the individual vehicle-specific ML models across the fleet and which on the other hand is used to to update and synchronize vehicle-specific ML models. While the vehicle-specific ML models are each trained based on vehicle-specific sensor and movement data, the fleet-wide ML model is not trained but synthesized. However, the synthesis improves the training status of the fleet-wide ML model in a similar way to conventional training of the fleet-wide ML model.
- the local, vehicle-specific ML models are merged or synthesized into an updated, fleet-wide ML model on the background device.
- the fleet-wide ML model formed in this way then represents a synthesis of the training results of all vehicle-specific ML models at a specific point in time, and the vehicle-specific ML models are preferably updated or synchronized with it again immediately after the synthesis.
- the synthesized, fleet-wide ML model is passed on from the background device via the update device to the vehicles in the vehicle fleet, so that due to the synchronization, each vehicle-specific ML model also benefits from the training results of all other vehicle-specific ML models.
- the merging (synthesizing) of the fleet-wide ML model and the subsequent updating (synchronization) of the vehicle-specific ML models is carried out with suitable data structures in such a way that no personal sensor and/or movement data is exchanged between the vehicles and the background system. Rather, only vehicle-specific or cross-fleet, representative model data is transmitted, which is derived from the vehicle-specific or cross-fleet ML models based on their respective training status.
- the underlying, person-related training data can no longer be extracted from this representative model data, because the model data relate to estimates of transmission qualities of potential radio connections, which were extrapolated from the sensor data and thus alienate them in such a way that they are no longer of any value to unauthorized persons be able.
- the vehicle-specific model data which are derived from the relevant vehicle-specific ML models, preferably represent a difference or a difference between the current state of the relevant vehicle-specific ML model and the state of this ML model after its last update.
- the vehicle-specific model data which is finally merged into the fleet-wide ML model, therefore preferably relates to increments of the training states or incremental training progress of the respective vehicle-specific ML model between two training phases or two points in time within a training phase.
- the fleet-wide model data which are derived from the fleet-wide ML model for synchronizing the vehicle-specific ML models, also represent a difference or a difference between the current state of the fleet-wide ML model and the state of this ML model after its last synthesis from the vehicle-specific ML models.
- the vehicle-specific ML models updated in this way are then based on the sensors collected individually from this vehicle in the further course. sensor and movement data is further trained so that the various vehicle-specific ML models diverge again after they have been synchronized. The resulting differences are extracted again at a suitable point in time in the form of vehicle-specific model data from the respective vehicle-specific ML models and recombined to form the fleet-wide ML model. From the fleet-wide ML model synthesized in this way, predictions can then be made about the transmission quality of wireless connections based on the sensor data of all vehicles in the vehicle fleet.
- FIG. 1 shows a schematic of an update system according to the invention
- Fig. 3 is a schematic of the machine learning unit of one according to the invention
- FIG. 5 shows a third preferred embodiment of the updating method according to the invention.
- 1 shows an example of an update system according to the invention comprising a central background device 10 (HGE) and a number of update devices 30 (SAE) in data communication with it via suitable, usually wired data communication connections 20 .
- the updating devices 30 in turn maintain individual radio links 40 to a large number of vehicles 50 in a vehicle fleet, via which the updating devices 30 can operate data communication with the vehicles 50 for various purposes, for example for the purposes of remote maintenance, measuring values, sensor control or the like.
- the updating of software that is installed on the vehicles 50 is initiated via the radio links 40 according to specifications of the background device 10 .
- the vehicles 50 are equipped with complex electronic control and regulation systems, which are generally implemented as embedded modules (“embedded systems”) and perform a variety of tasks within a vehicle 50, such as engine and brake control, the control of assistance, safety and communication systems and the like more.
- These electronic control units usually called ECU or "Electronic Control Units”
- ECU Electronic Control Units
- microprocessors volatile and non-volatile memories
- peripheral and bus systems are equipped with microprocessors, volatile and non-volatile memories, peripheral and bus systems and are an operating software or firmware, for example according to a predetermined software architecture, such as the AUTOSAR standard (Automotive Open System Architecture).
- the software components of the operating software of a vehicle control must be updated regularly for security and performance reasons.
- the mode of operation and the interaction of the background device 10 with the updating devices 30 ensures that the software of each individual vehicle 50 is updated individually specified conditions are carried out, which ensure stable mobile radio connections 40 with sufficient transmission qualities or sufficient data transmission rates to the vehicles 50 in order to update the software in each case without interruption.
- FIGS. 2a and 2b The interaction and the data communication between the background device 10, an updating device 30 and the various vehicles 50 in a vehicle fleet whose software is to be updated is illustrated using the example of FIGS. 2a and 2b, the respective preferred embodiments of the updating method according to the invention illustrate.
- the background device 10 of FIG. 2a comprises a control unit 11 which controls the background device 10 and in particular the machine learning unit 12 (ML unit).
- the ML unit 12 is implemented as a software program that can be executed on a processor (not shown) of the background device 10 and generates, processes, manages and uses two selected data structures, namely on the one hand the machine learning model 13 (ML model) and on the other hand, the update plan 14.
- ML model machine learning model 13
- the update plan 14 are stored in a suitable memory (not shown) of the backend facility 10 to which the ML unit 12 has access.
- the background device 10 instructs the updating device 30 in a step S1 to identify all vehicles 50 whose current software is running the current software is to be replaced.
- the updating device 30 is transferred in particular the version number(s) of the software to be updated, as well as other identification criteria that enable the identification of all affected n vehicles 50, such as model information and model numbers relating to the electronic control units, vehicle types, registration dates or the like.
- an identification unit 31 of the updating device 30 then compiles a list L of all vehicles 50 that correspond to the identification criteria transmitted by the background device 10 .
- information is obtained from the vehicles 50 via the radio links 40, which information may be required to identify the affected vehicles 50, for example operating states, error codes or the like.
- the list L of the identified vehicles 50 is transferred to the background device 10 and there to the ML unit 12.
- the identification unit 31 also transmits time specifications Z to the background device 10, which can also be based on the information received from the vehicles 50 in step S3.
- time specifications Z relate in particular to information about the duration of an update campaign in question or the "rollout" in days or weeks, i.e. the time window in which the software update of all identified vehicles 50 should be completed, and possibly information about the duration of an individual update on one specific vehicle, which is generally dependent on the specific technical infrastructure of the vehicle in question 50.
- the list L with the identified vehicles 50 and the time specifications Z are transferred to the machine learning unit 12 in step S4 and there as input values for a prediction of suitable update conditions B for the identified vehicles 50 based on the ML model 13 used, which finally combined to form an update plan 14 define the complete update campaign, ie the chronological/spatial sequence the software update of all vehicles 50 specified in list L within the time specification Z with regard to the duration of the campaign.
- Step S8 combines the two operating phases of the ML unit 12, namely firstly the training of the ML model 13 based, among other things, on sensor data D that the ML unit 12 receives in step S7, and secondly the prediction of Update conditions B and an update plan 14 based on the list L and the timing Z, which the ML unit 12 receives in step S4.
- 3 shows the two corresponding modules of the ML unit, namely the training module 12a, which trains the ML model 13 in step S8a, and the prediction module 12b, which derives update conditions B therefrom in step S8b.
- the ML model 13 is prepared for the prediction of update conditions B by generating a multidimensional map of the mobile radio network from problem-specific, exemplary training data, which, with specific spatial and time resolutions, can be used to make predictions about the transmission qualities Q of future radio links 40 mapped or modeled.
- problem-specific training data sensor data D from the vehicles 50 in particular are collected in steps S5 to S7 and made available to the ML unit 12, the specifically measured transmission qualities Q in as many radio cells of the mobile network and relate to as many points in time as possible.
- the vehicles 50 are equipped with suitable sensors and measuring devices, so that in step S5 they take measurements with regard to the transmission qualities Q within the radio cells visited by the vehicles 50 and transmit them as sensor data D to a sensor data module 32 of the updating device 30 .
- the sensors are suitably activated and deactivated in order to reliably obtain the desired sensor data D. mean, on the basis of which the ML model 13 is trained.
- the sensor data also relate to time, date and location data, the latter for example in the form of the radio cell IDs of the measured radio network.
- movement profiles of the vehicles 50 are also logged, for example in the form of GPS data, and made available to the sensor data module 32 .
- the sensor data module 32 prepares the sensor data D of the vehicles 50 in a suitable manner and finally makes them available to the ML unit 12 as training data for the ML model 13 in step S7.
- the sensor data module 32 prepares the movement profiles of the vehicles 50 in particular in such a way that movement data T with the best possible temporal and spatial resolution for each vehicle 50 is transferred to the ML unit, which particularly includes the times and routes of regular journeys identify the vehicle 50 in question, for example, regular trips to and from a place of work.
- the individual movement data T also show the different driving behavior on the individual days of the week, for example due to part-time work, home office days and other weekly trips.
- both training and prediction take place within the framework of step S8, a chronological sequence or dependency between training and prediction, and thus of steps S1 to S4 on the one hand and steps S5 to S7 on the other hand, requires the embodiment according to FIG .2a not. Rather, these two groups of steps can be interlinked in almost any way, for example in such a way that step S1 begins between steps S5 and S6 or that step S4 takes place at the same time as step S7.
- this means that the ML model 13 according to the embodiment according to FIG. 2a is continuously trained based on ever new, current sensor data D, which are continuously supplied as part of step S7 will.
- the ML-ModeU 13 is designed to be learning because it constantly adapts to current changes in the connection qualities Q and/or the movement data T of the vehicles 50 .
- a prediction for determining update conditions B can therefore be carried out at any time and is always based on the ML model 13 that is current at the relevant point in time. The same prediction request can therefore result in different update conditions B at a later point in time due to a more up-to-date ML model 13 .
- FIG. 1 the ML model 13 according to the embodiment according to FIG. 2a is continuously trained based on ever new, current sensor data D, which are continuously supplied as part of step S7 will.
- the ML-ModeU 13 is designed to be learning because it constantly adapts to current changes in the connection qualities Q and/or the movement data T of the vehicles 50 .
- the ML unit 12 is divided into a training module 12a and a prediction module 12b, as shown in FIG.
- This specific embodiment assumes that the training phase of the ML model 13 according to step S8a is first fully completed before the prediction phase according to step S8b begins.
- steps S5 to S8a are first carried out and only then when a stable, trained
- Steps S1 to S4, S5 to S7, S9 and S10 are technically identical in FIGS. 2a and 2b, only the order of execution differs in the two embodiments, as does the differentiation of step S8 according to FIG. 2a into two separate substeps
- the sensor data D and movement data T determined by the vehicles 50 and processed by the sensor data module 32 are used to assign transmission qualities Q to the radio cells at the relevant times. Those radio cells or those points in time or time intervals for which no sensor data D were collected, When training the ML model 13, transmission qualities Q derived from the existing sensor data D are assigned in order in this way to also complete the map with regard to those radio cells and time intervals for which no original sensor data D are available. This can also occur, for example, if only contradictory sensor data D is available for a radio cell or if insufficient or sufficiently reliable sensor data D could be collected.
- Transmission qualities Q are derived as part of the training based on similarity criteria between network cells and/or specific characteristics of radio links.
- the physical proximity of a radio cell without usable sensor data D to a radio cell with usable sensor data D is, for example, a simple similarity criterion.
- Other meaningful similarity criteria can be the time-dependent traffic density or the number of network participants, both of which can be derived from the movement data T, or also the buildings and, in principle, any suitable criterion that influences the data rate of a radio link.
- Suitable update conditions B for the identified vehicles 50 are then predicted with the trained ML model 13 and combined into an update plan 14 that allows the software to be installed on as many vehicles 50 as possible without interruption and within the specified time period of an update campaign .
- the update conditions B are determined based on the movement data T of the affected vehicles. They define one or more possible radio connections along the logged routes of the vehicles 50 40, through which the software can be updated.
- the update conditions B specify specific locations, for example in the form of radio cells regularly visited by the vehicle 50 in question, and corresponding times, at which the ML model 13 predicts a radio connection 40 with a sufficient transmission quality to the software of this Update vehicle 50 without disruption.
- the ML model 13 ultimately makes this prediction based on the sensor data D and the transmission qualities Q derived from it during the training.
- the movement data T form important secondary conditions in the prediction of suitable update conditions B because they limit the radio connections 40 that can potentially be used for software updating to the sensible radio connections 40 that a vehicle 50 can set up at all within the scope of its use. From these useful radio links 40 that the vehicle 50 can set up on its regular journeys, the ML model 13 determines those that probably offer sufficient transmission qualities Q to ensure the uninterrupted updating of the software.
- the ML model 13 predicts update conditions B for all vehicles 50 that are listed in the list L, which presumably allow an uninterrupted e software update.
- conflicts between the update conditions B of different vehicles 50 are avoided and, on the other hand, a global cost or loss function (“loss function”) is optimized or minimized, which becomes optimal/minimal precisely when for all in the list L listed vehicles 50 update conditions B can be found, which guarantee an uninterrupted software update with a high degree of probability are not only optimal for individual vehicles 50, but for the update campaign as a whole.
- step S9 the update plan 14 is finally transferred to the update device 30 or its update module 33, so that in step S10 the update campaign is prepared and in step S11 instructions are given via the radio links 40 to the vehicles 50 in question to update their software .
- FIG. 3 illustrates the ML unit 12 divided into its two already mentioned modules, namely the training module 12a and the prediction module 12b.
- the training step S8a carried out by the training module 12a
- the prediction step S8b carried out by the module 12b.
- the embodiment according to FIG. 2a provides that both modules are used in parallel in the sense that a prediction (step S8b) is carried out at any time based on the current state of the ML model 13, while the "learning" ML model 13 is continuously trained with ever new sensor data D (step S8a).
- the update campaign is trained for a certain period of time and is then, trained out, used to determine the update plan 14 without taking trends and changes into account while learning.
- step S7 the training module 12a receives sensor data D and movement data T, from which transmission qualities Q with the highest possible temporal and spatial resolution are derived.
- the ML model 13 thus models the above-mentioned map of the transmission qualities Q in the training step S8a.
- the prediction step S8b is then carried out with the sufficiently trained ML model 13, the training module 12a movement data T transferred to the prediction module 12b and the list L of the identified vehicles 50 provided in step S4 as well as the time specifications Z.
- update conditions B for all vehicles 50 of the list L are finally based on predictions with regard to the transmission qualities Q is determined and from this an update plan 14 is formed, which defines when and on which specific trip the software of each vehicle 50 is to be updated.
- FIG. 4 illustrates the implementation of the update plan 14 and the associated update conditions B.
- the update plan 14 is transferred to an update module 33 of the update unit 30, which then starts and monitors the update campaign.
- the update conditions B relating to these vehicles 50 are transferred to the identified vehicles 50 or to the corresponding control devices CNTL of these vehicles 50 in step S11.
- the control devices CNTL of the vehicles 50 thus independently monitor the presence of the respective update conditions B.
- the software SW is then updated by the control device CNTL in step S12 if the update conditions B apply, if the driving - zeug 50 is within the predetermined time interval in the / the predetermined radio cell / n or drives through it.
- the current software SW* is downloaded via the radio link 40, stored in the memory 51 and installed.
- FIG. 5 shows a third preferred embodiment of the updating method according to the invention, which is based on the second preferred embodiment according to FIG. 2b.
- FIG. 5 differs from FIG. 2b only with regard to steps S5 to S8a of FIG. 2b, which are replaced in FIG. 5 by steps S5, S6 and S7a to S7d. Steps S5, S6 and S7a to S7d according to FIG. 5 can just as well be supplemented in the embodiment according to FIG. 2a.
- the background device 10 comprises a synthesis module 12c, which synthesizes a fleet-wide ML model 13a in the manner described below.
- the updating device 30 comprises a forwarding module 34 which ensures bidirectional data communication between the background device 10 and the vehicles 50 .
- the vehicles 50 each have their own sensor data module 53, which provides the relevant vehicle 50 with the functionality of the sensor data module 32 in FIG. 2a, as well as a training and synchronization module 52, which on the one hand tion of the training module 12a according to FIG.
- the central functions of the training module 12a and the sensor data module 32 according to FIG. 2b are conceptually decentralized and integrated into each vehicle 50 of the vehicle fleet.
- Steps S1 through S4 and S9 through S11 according to FIG. 5 are identical to the correspondingly numbered steps in FIGS. 2a and 2b.
- Step S8b is also identical in the embodiments according to FIGS. 2b and 5.
- step S5 according to FIG. 5 in a vehicle 50 vehicle-specific
- Measurements regarding the transmission qualities Q are made within the radio cells visited by the vehicles 50 in question and are made available to the sensor data module 53 as sensor data D of the vehicle 50 in question.
- the sensor data module 53 prepares the sensor data D and the individual data analogously to the function of the sensor data module 32 according to FIGS
- the training and synchronization module 52 trains the vehicle-specific ML model 13b of the vehicle 50 with the vehicle-specific sensor and movement data D, T analogously to the function of the training module 12c according to FIG. 2b.
- Steps S7b to S7e relate to the process of synthesizing (S7b, S7c) the fleet-wide ML model 13a, i.e. merging it from the vehicle-specific ML models 13b, and synchronizing (S7d, S7e) the respective vehicle-specific ML models 13b, i.e their update based on the synthesized fleet-wide ML model 13a.
- the individual training progress of all vehicle-specific ML models 13b is bundled and made available to each individual vehicle-specific ML model 13b by means of steps S7b to S7e, in order thereby to improve the overall training quality.
- step S7b there is a stable, trained, vehicle-specific ML model 13b on a vehicle 50, the predictions regarding the Transmission qualities Qb of radio connections based on the sensor data D of the respective vehicle allowed.
- the radio links evaluated in this way can only come from radio cells that the relevant vehicle 50 has actually visited, for which the vehicle has therefore determined sensor data D or movement data T.
- each vehicle-specific ML model 13b is gradually provided with more and more information about radio connections in radio cells that other vehicles 50 of the vehicle fleet have visited, so that the relevant vehicle-specific ML model 13b iteratively forms an ever better basis for predicting the transmission qualities Qb of radio links in the radio cells visited, since the relevant vehicle-specific ML model 13b acquires more and more contextual knowledge about other areas of the radio network.
- all vehicles 50 in the vehicle fleet send vehicle-specific model data Mb to the forwarding module 34 of the updating device 30, which forwards the multitude of model data Mb to the synthesis module 12c of the background device 10 by vehicle or already bundled.
- the respective training and synchronization module 52 generates incremental model data Mb as the vehicle-specific model data Mb of each vehicle-specific ML model 13b, which represents the difference between the training state of the relevant vehicle-specific ML model 13b at the current time (i.e. at the time of executing the Step S7b) and the
- the incremental vehicle-specific model data Mb of individual or all vehicles 50 are combined in step S7c by the synthesis module 12c and synthesized to form a current fleet-wide ML model 13a, which then contains the current training results of all vehicle-specific ML models 13b .
- the fleet-wide ML model 13a like the ML models 13 according to the embodiments according to FIGS. 2a and 2b, represents a stable, trained, fleet-wide ML model, which forms the basis for the subsequent prediction phase the step S8b and the derivation of update conditions B is.
- the difference between the embodiment according to FIG. 5 and the embodiments according to FIGS. 2a and 2b is, among other things, that the fleet-wide ML model 13a and the transmission qualities Qa have the same training quality and a comparable prediction potential as the ML model 13 according to Figures 2a and 2b, that the fleet-wide ML model 13a does not come about through its own training phase, which would necessarily have to be based on the sensitive, personal sensor data D and movement data T, but through the synthesis step S7c, in in which only incremental model data Mb that are unproblematic with regard to any data protection provisions are combined.
- the training takes place in the local steps S7a on the individual vehicles 50, so that the respective sensor data do not leave these vehicles 50.
- the subsequent steps S7d and S7e relate to synchronization or updating of the individual vehicle-specific ML models 13b on fleet-wide, incremental model data Ma, which are extracted from the fleet-wide ML model 13a in step S7d.
- the incremental model data Ma represent the difference between the training status of the fleet-wide ML model 13a and the current one
- step S7d After the fleet-wide model data Ma have been sent from the synthesis module 12c via the forwarding module 34 of the updating device 30 to the respective training and synchronization modules 52 of the individual vehicles 50 in step S7d, on all of these vehicles 50 the relevant vehicle-specific ML model 13b updated with the fleet-wide model data Ma. After that, all vehicle-specific ML models 13b are synchronized and at this point represent the training status of the fleet-wide ML model 13a before the individual vehicle-specific ML models 13b diverge again as part of the respective vehicle-specific training by continuing to do so based on the vehicle-specifically collected sensor data D are further trained in a renewed step S7a.
- This process consisting of the synthesis of the overall fleet ML model 13a through steps S7b and S7c and the synchronization of the vehicle-specific ML models 13b through steps S7d and S7e can be repeated regularly, for example after specified time intervals have elapsed.
- the process of steps S7a to S7e can also be initiated by specific events, for example if sufficient training progress has been made with individual, a specific number or all vehicle-specific ML models 13b, or if sufficient new sensor data D were collected, which make a renewed synthesis/synchronization necessary.
- the vehicle-specific model data Mb can be generated synchronously from the individual vehicle-specific ML models 13b and made available to the forwarding module 34 almost at the same time.
- the forwarding module 34 can already bundle the vehicle-specific model data Mb of the vehicles 50 and forward them to the synthesis module 12c as a data set.
- the synthesis module 12c would then combine this data set with the fleet-wide ML model 13a and thus form a new fleet-wide ML model 13a that combines the training progress of all vehicle-specific ML models.
- the vehicles 50 can each send their vehicle-specific model data Mb independently of one another to the forwarding module 34 and temporarily stored by the latter and only forwarded in bundles to the synthesis module 12c when a sufficiently large data set of vehicle-specific model data Mb from different vehicles 50 is available.
- a practical and non-limiting example of an ML model 13, as described in connection with Figures 2 to 5, has output or result classes (output) for uninterrupted mobile radio connections of different durations:
- the ML model 13 includes a classifier based on decision trees, such as a random forest classifier or an extreme gradient boosting classifier.
- classifiers can be operated efficiently with the hardware of a vehicle 50 even with the limited resources in a vehicle 50 and with small training data sets, because they can be trained quickly and can be easily parallelized.
- the specific definition of the output classes and the specific features is selected or configured depending on certain preconditions, for example depending on the region in which the relevant vehicles 50 are moving, or on seasonal or cultural circumstances or the like.
- the vehicles 50 are equipped with pre-trained ML models 13 (or fleet-wide ML models 13a), which are then further trained individually in the relevant vehicles 50 and then form vehicle-specific ML models 13b.
- the pre-trained ML model 13 includes assignments of the probabilities of occurrence of the output classes to the various locations and directions of travel, illustrated using the two categories “location” and “direction of travel”.
- a specific combination of location and driving direction is assigned the vector (0.06; 0.13; 0.18; 0.22; 0.26; 0.12; 0.03), which means that in the In the relevant situation, statistically 6% of all mobile phone connections were stable or uninterrupted between 0 and 5 minutes, 13% of all mobile phone connections were stable or uninterrupted between 5 and 10 minutes, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102020004570.7A DE102020004570A1 (de) | 2020-07-24 | 2020-07-24 | Software-Aktualisierung über eine Funkverbindung |
| PCT/EP2021/025273 WO2022017645A1 (de) | 2020-07-24 | 2021-07-22 | Software-aktualisierung über eine funkverbindung |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4185951A1 true EP4185951A1 (de) | 2023-05-31 |
Family
ID=77168200
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP21749092.9A Pending EP4185951A1 (de) | 2020-07-24 | 2021-07-22 | Software-aktualisierung über eine funkverbindung |
Country Status (3)
| Country | Link |
|---|---|
| EP (1) | EP4185951A1 (de) |
| DE (1) | DE102020004570A1 (de) |
| WO (1) | WO2022017645A1 (de) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12288059B2 (en) | 2023-01-27 | 2025-04-29 | Toyota Motor North America, Inc. | Over the air analytics |
| DE102023209901A1 (de) * | 2023-10-10 | 2025-04-10 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zum Durchführen eines Updates eines Steuergeräts in einem Fahrzeug |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102009060358A1 (de) | 2009-12-24 | 2011-06-30 | Volkswagen AG, 38440 | Kommunikationssystem für Kraftfahrzeuge |
| US9549291B2 (en) | 2014-03-31 | 2017-01-17 | Ford Global Technologies, Llc | Crowd enhanced connectivity map for data transfer intermittency mitigation |
| DE102017205479B4 (de) | 2017-03-31 | 2024-08-29 | Audi Ag | Verfahren zur Vorhersage einer Mobilfunksignalstärke einer Mobilfunkanbindung eines Kraftfahrzeugs und Servervorrichtung zum Ausführen des Verfahrens |
| US10496394B2 (en) * | 2018-02-22 | 2019-12-03 | Ford Global Technologies, Llc | Cloud-based dynamic optimization of vehicle software updates |
| US10812624B2 (en) * | 2018-09-14 | 2020-10-20 | Cisco Technology, Inc. | Firmware/software over the air (FOTA) scheduling for connected vehicles |
-
2020
- 2020-07-24 DE DE102020004570.7A patent/DE102020004570A1/de active Pending
-
2021
- 2021-07-22 EP EP21749092.9A patent/EP4185951A1/de active Pending
- 2021-07-22 WO PCT/EP2021/025273 patent/WO2022017645A1/de not_active Ceased
Also Published As
| Publication number | Publication date |
|---|---|
| DE102020004570A1 (de) | 2022-01-27 |
| WO2022017645A1 (de) | 2022-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3688538B1 (de) | Verfahren und system zum aktualisieren eines steuerungsmodells für eine automatische steuerung zumindest einer mobilen einheit | |
| DE102017201789B4 (de) | Verfahren zum Betrieb eines Kraftfahrzeugs und Kraftfahrzeug | |
| EP1026649B1 (de) | Verfahren und Vorrichtung zur Bereitstellung von Verkehrsinformation | |
| EP2186077B1 (de) | Verfahren und vorrichtung zur steuerung des verkehrsflusses | |
| DE102019002790B4 (de) | Verfahren zur Prädiktion einer Verkehrssituation für ein Fahrzeug | |
| DE102017126167A1 (de) | Verfahren und vorrichtung zur fahrzeugfahrunterstützung | |
| DE102015111218A1 (de) | Parkmanagement für ein Fahrzeug | |
| DE102012201472A1 (de) | Verfahren zur Bereitstellung von Parkinformationen zu freien Parkplätzen | |
| EP3333823B1 (de) | Prognose einer signalisierung einer lichtsignalanlage mittels künstlicher intelligenz | |
| EP4185951A1 (de) | Software-aktualisierung über eine funkverbindung | |
| DE112021001592T5 (de) | Fahrzeuginterne steuervorrichtung, server und verifikationssystem | |
| DE102013000385A1 (de) | Verfahren und Navigationssystem zum Ermitteln eines Fahrroutenvorschlags für eine bevorstehende Fahrt mit einem Kraftwagen | |
| DE102014225122A1 (de) | Verfahren und System zur Bereitstellung von Informationen zur Verfügbarkeit von Ladestationen | |
| WO2023247089A1 (de) | Verfahren und vorrichtung zur prädiktion der wartezeit an einer ladestation | |
| DE102019122543A1 (de) | Verkehrsminderungssystem | |
| EP3437958A1 (de) | Abschätzen einer voraussichtlichen fahrzeit eines schienenfahrzeugs | |
| DE102014214757B4 (de) | Verfahren und Vorrichtung zum Erinnern eines Nutzers an einen Termin an einem entfernten Ort | |
| DE102020129016A1 (de) | Kontextmodellierung beim lernen eines benutzerverhaltens | |
| EP3709278B1 (de) | Erheben von fahrzeugbasierten, ortsbezogenen datensätzen | |
| EP0239827A2 (de) | Verfahren zum Ansteuern eines gemeinsamen Speichers eines aus einzelnen Mikroprozessorsystemen bestehenden Mehrprozessorsystems | |
| WO2023274585A1 (de) | Verfahren zum bereitstellen eines prädizierten, aktuellen fahrziels an einen nutzer eines fahrzeugs, computerlesbares medium, system, fahrzeug, und mobiles endgerät | |
| DE102021204191B4 (de) | Vorrichtung und Verfahren zur echtzeit-basierten dynamischen Verkehrszuordnung für zumindest zwei nachfolgende Fahrbahnen | |
| EP4700684A1 (de) | Verfahren zur ermittlung der verteilung der raumaufgelösten nutzung von verkehrsmitteln einer aus einer vielzahl an individuen bestehenden personenmenge in einem ermittlungszeitraum sowie ein das verfahren ausführendes system | |
| EP4700686A1 (de) | Verfahren zur ermittlung der verteilung der raumaufgelösten nutzung von verkehrsmitteln einer aus einer vielzahl an individuen bestehenden personenmenge in einem ermittlungszeitraum sowie ein das verfahren ausführendes system | |
| DE102009027544A1 (de) | Verfahren und Vorrichtung zur Ermittlung einer Verkehrsprognose |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
| 17P | Request for examination filed |
Effective date: 20230224 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
| RAP3 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: GIESECKE+DEVRIENT EPAYMENTS GMBH |
|
| DAV | Request for validation of the european patent (deleted) | ||
| DAX | Request for extension of the european patent (deleted) | ||
| RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: GIESECKE+DEVRIENT MOBILE SECURITY GERMANY GMBH |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
| 17Q | First examination report despatched |
Effective date: 20260116 |